© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3692
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function call argument

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]][
    -0.02
     each
    -0.01
    .read
    -0.01
    -0.01
    -0.01
    -0.01
     float
    -0.01
                ↵
    -0.01
    -0.01
    gram
    -0.01
    POSITIVE LOGITS
    N
    0.03
    n
    0.02
     N
    0.02
    row
    0.01
    150
    0.01
    09
    0.01
    120
    0.01
    07
    0.01
    08
    0.01
    300
    0.01
    Activations Density 64.390%

    No Known Activations